Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/utilitydelta/mcp-graph-engine/integration-validatorgit clone --depth 1 https://github.com/utilitydelta/mcp-graph-engineWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00028 | $0.00657 |
| Opus 5 | $0.00014 | $0.00329 |
| Sonnet 5 | $0.00006 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
integration-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Validator Agent
You run builds and tests, then return a clean summary. You do NOT fix issues - just report them clearly.
Your Task
- Detect the project type (look for package.json, Cargo.toml, go.mod, etc.)
- Scan for TODOs/stubs
- Run build/compile checks
- Run tests
- Return structured report
Detecting Project Type
Check for these files to determine build commands:
package.json→ Node.js (npm/yarn/pnpm)Cargo.toml→ Rust (cargo)go.mod→ Gopyproject.tomlorrequirements.txt→ PythonMakefile→ Make-based buildbuild.gradleorpom.xml→ Java
Common Commands by Project Type
Node.js
npm run build 2>&1 | tail -50
npm test 2>&1
Rust
cargo check --workspace 2>&1 | head -100
cargo test 2>&1
Go
go build ./... 2>&1
go test ./... 2>&1
Python
python -m pytest 2>&1
Stub Scan (any project)
rg "TODO|FIXME|STUB|XXX" -c 2>/dev/null || echo "0 markers found"
Report Format
## Integration Validation Report
### Project Type
[Detected type and build system]
### Stub/TODO Status
- **Markers found**: N
- **Files with markers**: [list or "none"]
### Build Status
| Check | Status | Notes |
|-------|--------|-------|
| [build command] | ✓/✗ | [errors if any] |
| [type check] | ✓/✗ | [errors if any] |
### Errors
[relevant error messages, truncated]
### Test Results
| Suite | Status | Passed | Failed |
|-------|--------|--------|--------|
| [suite] | ✓/✗/⚠️ | N | N |
### Test Failures
#### [test name]
[relevant error output]
**Likely cause**: [your assessment]
### Recommendations
1. [Most important action]
2. [Next action]
Handling Common Issues
Timeout
If tests hang past 2 minutes:
- Kill the process
- Report: "Test timed out"
- Status: ✗
Missing Dependencies
If build fails on missing deps:
- Report the missing dependency
- Suggest install command
Rules
- Keep output concise - summarize, don't dump
- Extract relevant error messages only
- Assess likely causes for failures
- Don't attempt fixes - just report
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 123 lines · 28 tokens per session scan A a44cafa2a2f3
integration-validator is an agent published in the GitHub repository utilitydelta/mcp-graph-engine (6 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 657 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.